Improvements of an Optical Scanning System for Indoor Localization Based on Defuzzification Methods

Abstract

Nowadays, artificial intelligence (AI) has revolutionized the industry and made it possible to develop systems that ensure safety in human-robot collaboration. Mobile and industrial robots need a point of reference in their orientation for avoiding obstacles. Device and sensor technologies, such as acoustic sensors, Global Positioning System (GPS), light detection and ranging (LiDAR), accelerometers, and digital cameras play an important role in providing high resolution and sensitivity to solve complex problems in the industry. However, their cost and the need of applying signal processing techniques to filter their signals may not offer the required reliability for critical applications, such as indoor localization methods for industrial robots. The optical scanning systems (OSS) are devices that can be used instead at a lower cost, compared to the costs of devices previously mentioned. Nevertheless, there is still the challenge of avoiding the filtering of the signal. In this paper, a method to determine the energy center from sensors of an OSS using AI techniques is introduced. It uses defuzzification algorithms to accomplish accuracy measurements for localization and navigation tasks. The advantage of this method is that it eliminates the need of using the filtering process. One of the main contributions of this work is that the results can be used to implement an accurate and efficient indoor localization system, which can be used by an autonomous vehicle, such as industrial robots. According to the statistical analysis carried out, the minimal difference between the real position and the position estimated by the OSS was 0.021°.